"Evaluating the model of classification and valuation of disabilities used in Brazil and defining the elaboration and adoption of a unique model for all the country": Brazilian Interministerial Workgroup Task

The President of Brazil established an Interministerial Work Group in order to “evaluate the model of classification and valuation of disabilities used in Brazil and to define the elaboration and adoption of a unique model for all the country”. Eight Ministries and/or Secretaries participated in the discussion over a period of 10 months, concluding that a proposed model should be based on the United Nations Convention on the Rights of Person with Disabilities, the International Classification of Functioning, Disability and Health, and the ‘support theory’, and organizing a list of recommendations and necessary actions for a Classification, Evaluation and Certification Network with national coverage.

A system for classification of time-series data from industrial non-destructive device

This work proposes a system for classification of industrial steel pieces by means of magnetic nondestructive device. The proposed classification system presents two main stages, online system stage and off-line system stage. In online stage, the system classifies inputs and saves misclassification information in order to perform posterior analyses. In the off-line optimization stage, the topology of a Probabilistic Neural Network is optimized by a Feature Selection algorithm combined with the Probabilistic Neural Network to increase the classification rate. The proposed Feature Selection algorithm searches for the signal spectrogram by combining three basic elements: a Sequential Forward Selection algorithm, a Feature Cluster Grow algorithm with classification rate gradient analysis and a Sequential Backward Selection. Also, a trash-data recycling algorithm is proposed to obtain the optimal feedback samples selected from the misclassified ones.

Gender classification in large databases

[EN]In this paper, we address the challenge of gender classi - cation using large databases of images with two goals. The rst objective is to evaluate whether the error rate decreases compared to smaller databases. The second goal is to determine if the classi er that provides the best classi cation rate for one database, improves the classi cation results for other databases, that is, the cross-database performance.

Improving gender classification accuracy in the wild

[EN]In this paper, we focus on gender recognition in challenging large scale scenarios. Firstly, we review the literature results achieved for the problem in large datasets, and select the currently hardest dataset: The Images of Groups. Secondly, we study the extraction of features from the face and its local context to improve the recognition accuracy. Diff erent descriptors, resolutions and classfii ers are studied, overcoming previous literature results, reaching an accuracy of 89.8%.

Fuzzy Online Reputation Analysis Framework

The fuzzy online reputation analysis framework, or “foRa” (plural of forum, the Latin word for marketplace) framework, is a method for searching the Social Web to find meaningful information about reputation. Based on an automatic, fuzzy-built ontology, this framework queries the social marketplaces of the Web for reputation, combines the retrieved results, and generates navigable Topic Maps. Using these interactive maps, communications operatives can zero in on precisely what they are looking for and discover unforeseen relationships between topics and tags. Thus, using this framework, it is possible to scan the Social Web for a name, product, brand, or combination thereof and determine query-related topic classes with related terms and thus identify hidden sources. This chapter also briefly describes the youReputation prototype (www.youreputation.org), a free web-based application for reputation analysis. In the course of this, a small example will explain the benefits of the prototype.

Diagnosing synaesthesia with online colour pickers: Maximising sensitivity and specificity

The most commonly used method for formally assessing grapheme-colour synaesthesia (i.e., experiencing colours in response to letter and/or number stimuli) involves selecting colours from a large colour palette on several occasions and measuring consistency of the colours selected. However, the ability to diagnose synaesthesia using this method depends on several factors that have not been directly contrasted. These include the type of colour space used (e.g., RGB, HSV, CIELUV, CIELAB) and different measures of consistency (e.g., city block and Euclidean distance in colour space). This study aims to find the most reliable way of diagnosing grapheme-colour synaesthesia based on maximising sensitivity (i.e., ability of a test to identify true synaesthetes) and specificity (i.e., ability of a test to identify true non-synaesthetes). We show, applying ROC (Receiver Operating Characteristics) to binary classification of a large sample of self-declared synaesthetes and non-synaesthetes, that the consistency criterion (i.e., cut-off value) for diagnosing synaesthesia is considerably higher than the current standard in the field. We also show that methods based on perceptual CIELUV and CIELAB colour models (rather than RGB and HSV colour representations) and Euclidean distances offer an even greater sensitivity and specificity than most currently used measures. Together, these findings offer improved heuristics for the behavioural assessment of grapheme-colour synaesthesia.

e-MIR2: a public online inventory of medical informatics resources

Background. Over the last years, the number of available informatics resources in medicine has grown exponentially. While specific inventories of such resources have already begun to be developed for Bioinformatics (BI), comparable inventories are as yet not available for Medical Informatics (MI) field, so that locating and accessing them currently remains a hard and time-consuming task. Description. We have created a repository of MI resources from the scientific literature, providing free access to its contents through a web-based service. Relevant information describing the resources is automatically extracted from manuscripts published in top-ranked MI journals. We used a pattern matching approach to detect the resources? names and their main features. Detected resources are classified according to three different criteria: functionality, resource type and domain. To facilitate these tasks, we have built three different taxonomies by following a novel approach based on folksonomies and social tagging. We adopted the terminology most frequently used by MI researchers in their publications to create the concepts and hierarchical relationships belonging to the taxonomies. The classification algorithm identifies the categories associated to resources and annotates them accordingly. The database is then populated with this data after manual curation and validation. Conclusions. We have created an online repository of MI resources to assist researchers in locating and accessing the most suitable resources to perform specific tasks. The database contained 282 resources at the time of writing. We are continuing to expand the number of available resources by taking into account further publications as well as suggestions from users and resource developers.

Recognition of online handwritten music symbols

Paper submitted to MML 2013, 6th International Workshop on Machine Learning and Music, Prague, September 23, 2013.

Improving classification using a Confidence Matrix based on weak classifiers applied to OCR

This paper proposes a new feature representation method based on the construction of a Confidence Matrix (CM). This representation consists of posterior probability values provided by several weak classifiers, each one trained and used in different sets of features from the original sample. The CM allows the final classifier to abstract itself from discovering underlying groups of features. In this work the CM is applied to isolated character image recognition, for which several set of features can be extracted from each sample. Experimentation has shown that the use of CM permits a significant improvement in accuracy in most cases, while the others remain the same. The results were obtained after experimenting with four well-known corpora, using evolved meta-classifiers with the k-Nearest Neighbor rule as a weak classifier and by applying statistical significance tests.

Improving kNN multi-label classification in Prototype Selection scenarios using class proposals

Prototype Selection (PS) algorithms allow a faster Nearest Neighbor classification by keeping only the most profitable prototypes of the training set. In turn, these schemes typically lower the performance accuracy. In this work a new strategy for multi-label classifications tasks is proposed to solve this accuracy drop without the need of using all the training set. For that, given a new instance, the PS algorithm is used as a fast recommender system which retrieves the most likely classes. Then, the actual classification is performed only considering the prototypes from the initial training set belonging to the suggested classes. Results show that this strategy provides a large set of trade-off solutions which fills the gap between PS-based classification efficiency and conventional kNN accuracy. Furthermore, this scheme is not only able to, at best, reach the performance of conventional kNN with barely a third of distances computed, but it does also outperform the latter in noisy scenarios, proving to be a much more robust approach.

Morphological classification of microtidal sand and gravel beaches

A new classification of microtidal sand and gravel beaches with very different morphologies is presented below. In 557 studied transects, 14 variables were used. Among the variables to be emphasized is the depth of the Posidonia oceanica. The classification was performed for 9 types of beaches: Type 1: Sand and gravel beaches, Type 2: Sand and gravel separated beaches, Type 3: Gravel and sand beaches, Type 4: Gravel and sand separated beaches, Type 5: Pure gravel beaches, Type 6: Open sand beaches, Type 7: Supported sand beaches, Type 8: Bisupported sand beaches and Type 9: Enclosed beaches. For the classification, several tools were used: discriminant analysis, neural networks and Support Vector Machines (SVM), the results were then compared. As there is no theory for deciding which is the most convenient neural network architecture to deal with a particular data set, an experimental study was performed with different numbers of neuron in the hidden layer. Finally, an architecture with 30 neurons was chosen. Different kernels were employed for SVM (Linear, Polynomial, Radial basis function and Sigmoid). The results obtained for the discriminant analysis were not as good as those obtained for the other two methods (ANN and SVM) which showed similar success.

On the suitability of Prototype Selection methods for kNN classification with distributed data

In the current Information Age, data production and processing demands are ever increasing. This has motivated the appearance of large-scale distributed information. This phenomenon also applies to Pattern Recognition so that classic and common algorithms, such as the k-Nearest Neighbour, are unable to be used. To improve the efficiency of this classifier, Prototype Selection (PS) strategies can be used. Nevertheless, current PS algorithms were not designed to deal with distributed data, and their performance is therefore unknown under these conditions. This work is devoted to carrying out an experimental study on a simulated framework in which PS strategies can be compared under classical conditions as well as those expected in distributed scenarios. Our results report a general behaviour that is degraded as conditions approach to more realistic scenarios. However, our experiments also show that some methods are able to achieve a fairly similar performance to that of the non-distributed scenario. Thus, although there is a clear need for developing specific PS methodologies and algorithms for tackling these situations, those that reported a higher robustness against such conditions may be good candidates from which to start.

O controlo interno e a implementação de auditorias online no Safex em contexto de e-governance: Tecnologias, desafios e oportunidades

O presente Relatório Detalhado de Atividade Profissional é apresentado no âmbito da obtenção do Grau de Mestre dos Oficiais do Exército licenciados pré-Bolonha pela Academia Militar na Área específica de Administração Militar. A sua redação e estruturação tem por base o definido na NEP 520 e NEP 517/1ª da AM, para esta tipologia de trabalhos, tendo o autor, optado por desenvolver um tema no âmbito da sua atividade profissional, considerado como pioneiro e inovador. O Tenente-Coronel de Administração Militar do Exército Português, Luís Miguel Gonçalves, nasceu a 25 de Novembro de 1971. Do seu percurso académico e formativo, consta frequência pré-Universitária, em estabelecimento militar de ensino, no Instituto Militar dos Pupilos do Exército, na área de Contabilidade e Administração; a Licenciatura em Ciências Militares, na especialidade de Administração Militar, pela Academia Militar, em 1995, com a Classificação final de 13,58 valores; o tirocínio para Oficiais de Administração Militar, com a nota final de 15,38 valores; o Curso de Operações Irregulares, tendo obtido a classificação de 17,67 valores; o Curso de Promoção a Capitão, com 16,63 valores; e o Curso de Promoção a Oficial Superior do Instituto de Altos Estudos Militares, com a classificação final de 14,50 valores. No âmbito da formação de pós-graduação, tem averbado créditos no módulo de Metodologia de Investigação Cientifica, pela Academia Militar, no Ano Letivo 2013/14, com a classificação final de 16,00 valores. Para além destes, o Environmental Course For Portugal – NATO School/ SHAPE; formação em Gestão de Projetos/ Exército - Microsoft Enterprise Project Management; o Curso de Formação Pedagógica Inicial de Formadores do Instituto de Emprego e Formação Profissional, com Homologação das Competências Pedagógicas; e vários certificados de formações no âmbito da Contabilidade, Administração, Finanças Públicas e Auditorias Financeiras, atribuídas pela Direção de Finanças do Exército e pelo Instituto de Gestão e Administração Pública do Porto. Ao longo dos 25 anos de serviço prestado ao Exército Português, como Oficial de Administração Militar, desempenhou diversos cargos e funções de Comando e Chefia, em várias UEO, nas áreas setoriais e funcionais, da formação, da instrução, da componente operacional, da logística, do pessoal, das finanças públicas, das inspeções e auditorias, da gestão e da Administração Militar. Atualmente o Tenente-Coronel Miguel Gonçalves, desempenha as Funções de Comandante de Batalhão na Escola dos Serviços. Para além dos cargos e funções averbadas no seu Curriculum Vitae detalhado, constituiu em 1996 o Núcleo Logístico de Projeção, Implantação, Acompanhamento e Ajuda Técnica no âmbito do emprego dos meios táticos e operacionais da Área de Responsabilidade FND/ IFOR na Bósnia-Herzegovina (Jugoslávia). Tem publicado na Revista da Administração Militar, vários artigos no âmbito da logística operacional, na função de combate Apoio de Serviços. Na área da formação, foi orientador e supervisor de vários trabalhos, individuais e de grupo aos cursos de promoção a capitão; e constitui-se como elemento primariamente responsável pelo planeamento e implementação dos primeiros cursos no Exército, com formação certificado pela Agência Nacional para a Qualificação e Ensino Profissional, I.P., do Sistema Nacional de Qualificações, certificação inserida no Catálogo Nacional de Qualificações. Na área Inspetiva, integrou várias equipas de Inspeção-Geral do Exército, como inspetor responsável pelas áreas de Logística e Finanças, bem como as de Inspetor, para a área dos recursos humanos – Despesas com Pessoal, nas equipas de inspeção do Comando do Pessoal do Exército. No desempenho das funções de Auditor Financeiro do Centro de Finanças do Comando do Pessoal, realizou diversas auditorias financeiras às UEO do Comando do Pessoal, na sua dependência, tendo desenvolvido e implementado um sistema pioneiro e inovador de monitorização e controlo interno, de auditorias “Online” com análise e reporte mensal, às contas das UEO do Comando do Pessoal, tendo em vista a validação das Demonstrações Financeiras para a Conta de Gerência Anual do Exército. A escolha do tema, “O Controlo Interno e a implementação de Auditorias Online no SAFEx em contexto de e-Governance: Tecnologias, desafios e oportunidades” surge na sequência da implementação destes procedimentos pelo autor, numa altura em que o Exército entrava em operativo com o Sistema Integrado de Gestão (SIG/DN), tendo sido à data reconhecido publicamente pelo TGEN Comandante do Pessoal do Exército, como sendo um procedimento inovador, com notáveis vantagens para a eficiência e eficácia do sistema administrativo-financeiro do Comando do Pessoal e consequentemente do Exército.

Can diversity amongst learners improve online object tracking?

We present a novel analysis of the state of the art in object tracking with respect to diversity found in its main component, an ensemble classifier that is updated in an online manner. We employ established measures for diversity and performance from the rich literature on ensemble classification and online learning, and present a detailed evaluation of diversity and performance on benchmark sequences in order to gain an insight into how the tracking performance can be improved. © Springer-Verlag 2013.

Implementação de uma arquitetura fuzzy neural em hardware com treinamento online

Computational Intelligence Methods have been expanding to industrial applications motivated by their ability to solve problems in engineering. Therefore, the embedded systems follow the same idea of using computational intelligence tools embedded on machines. There are several works in the area of embedded systems and intelligent systems. However, there are a few papers that have joined both areas. The aim of this study was to implement an adaptive fuzzy neural hardware with online training embedded on Field Programmable Gate Array – FPGA. The system adaptation can occur during the execution of a given application, aiming online performance improvement. The proposed system architecture is modular, allowing different configurations of fuzzy neural network topologies with online training. The proposed system was applied to: mathematical function interpolation, pattern classification and selfcompensation of industrial sensors. The proposed system achieves satisfactory performance in both tasks. The experiments results shows the advantages and disadvantages of online training in hardware when performed in parallel and sequentially ways. The sequentially training method provides economy in FPGA area, however, increases the complexity of architecture actions. The parallel training method achieves high performance and reduced processing time, the pipeline technique is used to increase the proposed architecture performance. The study development was based on available tools for FPGA circuits.